SOURCE-LINKED INTELLIGENCE

Robustness of Diffusion Models under Distribution Shift

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Score-based diffusion models are increasingly considered in settings where the underlying data distribution may differ from the training distribution, yet existing theoretical guarantees largely focus on the no-shift setting. In this work, we study robust score estimation under Wasserstein perturbations of a reference distribution. For the Ornstein--Uhlenbeck diffusion, we show that robust estimation decomposes into two fundamental components: the statistical cost of learning the reference distribution and the intrinsic cost of distribution shift. The latter scales quadratically with the Wasse

Read original source ↗ Open in workspace

recordType

paper

region

Global